Ilker ManapandClaude Opus 5.5 a00c92648e Status says when the cluster's alerts go nowhere ...

Setup asks for webhooks, but one left empty was never mentioned again: a
lost node or a judge down was told nobody. With no notify.webhooks in the
cluster's settings, ctl status and the console's Overview say so, and how
to set one. BACKLOG: the judge's refusal after a placement change, tried
again on idle VMs, did not happen; a cold judge's first answer is 2-3x
slower but inside its budget.

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>

2026-11-12 22:49:37 +01:00

..

adminapi

Status says when the cluster's alerts go nowhere

2026-11-12 22:49:37 +01:00

agentsvc

Slurm beside llmgw, P3 and P4: the leader hands nodes over; ctl slurm

2026-11-11 12:33:14 +01:00

catalog

Replicas counted per profile: seven on cards and four on CPUs under one name

2026-11-03 09:21:50 +01:00

fabrics

Watch each fabric's subnet managers, and keep a fabric one through a failover

2026-09-29 07:47:03 +02:00

fabrictest

Measure two nodes' fabric rail by rail: llmgw ctl fabric-test

2026-09-29 21:29:23 +02:00

facility

Facility-aware placement: racks, PDUs, holds and power caps

2026-10-05 01:17:49 +02:00

federation

Federation: another llmgw cluster as a provider, its models as PEER/MODEL

2026-10-05 01:21:30 +02:00

fleetmetrics

How much of each GPU works, beside whether anything does

2026-10-31 20:11:26 +01:00

inventory

How much of each GPU works, beside whether anything does

2026-10-31 20:11:26 +01:00

modelserve

The serve forms start at the longest context that fits

2026-11-08 14:38:41 +01:00

modelsvc

Replicas counted per profile: seven on cards and four on CPUs under one name

2026-11-03 09:21:50 +01:00

nvlink

Find multi-node NVLink domains, place across them, and show them as racks

2026-09-29 09:07:59 +02:00

placement

A model that failed to start is placed elsewhere next

2026-11-10 09:22:11 +01:00

quota

Guarantee and limit capacity per part of the tenancy tree

2026-09-30 18:15:38 +02:00

reconciler

A model that failed to start is placed elsewhere next

2026-11-10 09:22:11 +01:00

slurmsvc

Slurm's shared files and users: one path everywhere, accounts as Linux users

2026-11-12 21:34:34 +01:00

topology

Map every InfiniBand fabric, draw it, and place replicas by it

2026-09-29 08:46:23 +02:00

train

LoRA adapters trained on the nodes: llmgw ctl train

2026-10-08 20:25:57 +02:00

control_test.go

Give every engine a key only the router holds

2026-09-30 00:38:29 +02:00

control.go

Rate limits counted across the control planes with router.active_active

2026-11-01 17:30:08 +01:00

enginechoice.go

FreeToken, an engine for models larger than the card

2026-10-31 22:10:05 +01:00

external_test.go

Several keys for one outside provider

2026-10-17 08:56:30 +02:00

facility_test.go

Facility-aware placement: racks, PDUs, holds and power caps

2026-10-05 01:17:49 +02:00

facility.go

The cluster's settings live in the store, and every change takes effect

2026-10-05 15:25:23 +02:00

leadership_test.go

Leadership stays put while the store's primary is replaced

2026-10-15 23:17:58 +02:00

leadership.go

Leadership stays put while the store's primary is replaced

2026-10-15 23:17:58 +02:00

quotas.go

Scale and place by what a replica was measured to serve

2026-09-30 18:21:08 +02:00

routing_test.go

Rate limits counted across the control planes with router.active_active

2026-11-01 17:30:08 +01:00

routing.go

Rate limits counted across the control planes with router.active_active

2026-11-01 17:30:08 +01:00